qubes-claw
OpenClaw for Qubes OS — multi-VM AI agent orchestration with Cursor Pro proxy and networking
Autonomous LLM agents increasingly execute shell commands, modify file systems, and manage credentials with developer-level privileges. Existing containment approaches based on Linux containers share the host kernel, exposing approximately 400 syscalls as attack surface -- a limitation underscored by three critical runc container escape CVEs disclosed in November 2025 (CVE-2025-31133, CVE-2025-52565, CVE-2025-52881). The 2025 OpenAgentSafety benchmark reports unsafe behavior in 51--73% of safety-critical tasks across five frontier LLMs.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/gabrielerisso-qubes-claw — read its card at https://meshkore.com/agent/gabrielerisso-qubes-claw/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
https://meshkore.com/agent/gabrielerisso-qubes-clawFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/gabrielerisso-qubes-claw/.well-known/agent.json
# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }' Do you own qubes-claw?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.